50 citations · 157 across the 31 of their papers we have counts for
31 papers
Artifact Feature Purification for Cross-domain Detection of AI-generated Images
Zheling Meng, Bo Peng, Jing Dong +1
In the era of AIGC, the fast development of visual content generation technologies, such as diffusion models, bring potential security risks to our society. Existing generated imag…
GaFET: Learning Geometry-aware Facial Expression Translation from In-The-Wild Images
Tianxiang Ma, Bingchuan Li, Qian He +2
While current face animation methods can manipulate expressions individually, they suffer from several limitations. The expressions manipulated by some motion-based facial reenactm…
Freestyle 3D-Aware Portrait Synthesis Based on Compositional Generative Priors
Tianxiang Ma, Kang Zhao, Jianxin Sun +2
Efficiently generating a freestyle 3D portrait with high quality and 3D-consistency is a promising yet challenging task. The portrait styles generated by most existing methods are…
RiDDLE: Reversible and Diversified De-identification with Latent Encryptor
Dongze Li, Wei Wang, Kang Zhao +2
This work presents RiDDLE, short for Reversible and Diversified De-identification with Latent Encryptor, to protect the identity information of people from being misused. Built upo…
Collaborative Feature Learning for Fine-grained Facial Forgery Detection and Segmentation
Weinan Guan, Wei Wang, Jing Dong +2
Detecting maliciously falsified facial images and videos has attracted extensive attention from digital-forensics and computer-vision communities. An important topic in manipulatio…
DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation
Yueming Lyu, Tianwei Lin, Fu Li +3
Text-driven image manipulation remains challenging in training or inference flexibility. Conditional generative models depend heavily on expensive annotated training data. Meanwhil…
Designing a 3D-Aware StyleNeRF Encoder for Face Editing
Songlin Yang, Wei Wang, Bo Peng +1
GAN inversion has been exploited in many face manipulation tasks, but 2D GANs often fail to generate multi-view 3D consistent images. The encoders designed for 2D GANs are not able…
CFFT-GAN: Cross-domain Feature Fusion Transformer for Exemplar-based Image Translation
Tianxiang Ma, Bingchuan Li, Wei Liu +3
Exemplar-based image translation refers to the task of generating images with the desired style, while conditioning on certain input image. Most of the current methods learn the co…
Semantic 3D-aware Portrait Synthesis and Manipulation Based on Compositional Neural Radiance Field
Tianxiang Ma, Bingchuan Li, Qian He +2
Recently 3D-aware GAN methods with neural radiance field have developed rapidly. However, current methods model the whole image as an overall neural radiance field, which limits th…
Visual Realism Assessment for Face-swap Videos
Xianyun Sun, Beibei Dong, Caiyong Wang +2
Deep-learning based face-swap videos, also known as deep fakes, are becoming more and more realistic and deceiving. The malicious usage of these face-swap videos has caused wide co…
DFGC 2022: The Second DeepFake Game Competition
Bo Peng, Wei Xiang, Yue Jiang +5
This paper presents the summary report on our DFGC 2022 competition. The DeepFake is rapidly evolving, and realistic face-swaps are becoming more deceptive and difficult to detect.…
DRAN: Detailed Region-Adaptive Normalization for Conditional Image Synthesis
Yueming Lyu, Peibin Chen, Jingna Sun +3
In recent years, conditional image synthesis has attracted growing attention due to its controllability in the image generation process. Although recent works have achieved realist…
DFGC 2021: A DeepFake Game Competition
Bo Peng, Hongxing Fan, Wei Wang +20
This paper presents a summary of the DFGC 2021 competition. DeepFake technology is developing fast, and realistic face-swaps are increasingly deceiving and hard to detect. At the s…
Transferable Sparse Adversarial Attack
Ziwen He, Wei Wang, Jing Dong +1
Deep neural networks have shown their vulnerability to adversarial attacks. In this paper, we focus on sparse adversarial attack based on the norm constraint, which can su…
Robust Face-Swap Detection Based on 3D Facial Shape Information
Weinan Guan, Wei Wang, Jing Dong +2
Maliciously-manipulated images or videos - so-called deep fakes - especially face-swap images and videos have attracted more and more malicious attackers to discredit some key figu…
SOGAN: 3D-Aware Shadow and Occlusion Robust GAN for Makeup Transfer
Yueming Lyu, Jing Dong, Bo Peng +2
In recent years, virtual makeup applications have become more and more popular. However, it is still challenging to propose a robust makeup transfer method in the real-world enviro…
Exploring Adversarial Fake Images on Face Manifold
Dongze Li, Wei Wang, Hongxing Fan +1
Images synthesized by powerful generative adversarial network (GAN) based methods have drawn moral and privacy concerns. Although image forensic models have reached great performan…
MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation
Tianxiang Ma, Bo Peng, Wei Wang +1
Pose-guided person image generation usually involves using paired source-target images to supervise the training, which significantly increases the data preparation effort and limi…
Learning Pose-invariant 3D Object Reconstruction from Single-view Images
Bo Peng, Wei Wang, Jing Dong +1
Learning to reconstruct 3D shapes using 2D images is an active research topic, with benefits of not requiring expensive 3D data. However, most work in this direction requires multi…
Temporal Sparse Adversarial Attack on Sequence-based Gait Recognition
Ziwen He, Wei Wang, Jing Dong +1
Gait recognition is widely used in social security applications due to its advantages in long-distance human identification. Recently, sequence-based methods have achieved high acc…
A New Ensemble Method for Concessively Targeted Multi-model Attack
Ziwen He, Wei Wang, Xinsheng Xuan +2
It is well known that deep learning models are vulnerable to adversarial examples crafted by maliciously adding perturbations to original inputs. There are two types of attacks: ta…
Scalable Fine-grained Generated Image Classification Based on Deep Metric Learning
Xinsheng Xuan, Bo Peng, Wei Wang +1
Recently, generated images could reach very high quality, even human eyes could not tell them apart from real images. Although there are already some methods for detecting generate…
AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization
Xiao-Yu Zhang, Changsheng Li, Haichao Shi +3
The point process is a solid framework to model sequential data, such as videos, by exploring the underlying relevance. As a challenging problem for high-level video understanding,…
On the generalization of GAN image forensics
Xinsheng Xuan, Bo Peng, Wei Wang +1
Recently the GAN generated face images are more and more realistic with high-quality, even hard for human eyes to detect. On the other hand, the forensics community keeps on develo…